Local LLM Finder

Find the local LLM that fits your hardware

Local LLM Finder!!!! — Enter your GPU, CPU and RAM to rank the local LLMs that fit your hardware, with benchmark scores.

How to use Local LLM Finder

  1. Select your GPU or enter custom VRAM and RAM
  2. Choose a quantization and speed filter
  3. See the ranked models that fit
  4. Copy the Ollama run command for your pick

Features

  • GPU, RAM and bandwidth based ranking
  • Real whichllm quant size math
  • Full VRAM, offload and RAM-only fit types
  • Speed estimates in tokens per second
  • Ollama run command for every model
  • GPU-only and speed filters

Frequently asked questions

Is it free?

Yes, unlimited.

Login to use this free online tool. Create a free account to get started.